Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475921" target="_blank" >RIV/00216208:11320/23:10475921 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.findings-acl.350" target="_blank" >https://aclanthology.org/2023.findings-acl.350</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

Popis výsledku v původním jazyce

Multilingual language models have recently gained attention as a promising solution for representing multiple languages in a single model. In this paper, we propose new criteria to evaluate the quality of lexical representation and vocabulary overlap observed in sub-word tokenizers.Our findings show that the overlap of vocabulary across languages can be actually detrimental to certain downstream tasks (POS, dependency tree labeling). In contrast, NER and sentence-level tasks (cross-lingual retrieval, NLI) benefit from sharing vocabulary. We also observe that the coverage of the language-specific tokens in the multilingual vocabulary significantly impacts the word-level tasks. Our study offers a deeper understanding of the role of tokenizers in multilingual language models and guidelines for future model developers to choose the most suitable tokenizer for their specific application before undertaking costly model pre-training.

Název v anglickém jazyce

Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

Popis výsledku anglicky

Multilingual language models have recently gained attention as a promising solution for representing multiple languages in a single model. In this paper, we propose new criteria to evaluate the quality of lexical representation and vocabulary overlap observed in sub-word tokenizers.Our findings show that the overlap of vocabulary across languages can be actually detrimental to certain downstream tasks (POS, dependency tree labeling). In contrast, NER and sentence-level tasks (cross-lingual retrieval, NLI) benefit from sharing vocabulary. We also observe that the coverage of the language-specific tokens in the multilingual vocabulary significantly impacts the word-level tasks. Our study offers a deeper understanding of the role of tokenizers in multilingual language models and guidelines for future model developers to choose the most suitable tokenizer for their specific application before undertaking costly model pre-training.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Findings of the Association for Computational Linguistics: ACL 2023

ISBN

978-1-959429-62-3

ISSN

—

e-ISSN

—

Počet stran výsledku

21

Strana od-do

5661-5681

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Toronto, Canada

Datum konání akce

9. 7. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—